Abstract
Recent studies suggest the brain functional connectivity impairment is the early event occurred in case of Alzheimer’s disease (AD) as well as mild cognitive impairment (MCI). We model the brain as a graph based network to study these impairment. In this paper, we present a new diagnosis approach using graph theory based features from functional magnetic resonance (fMR) images to discriminate AD, MCI, and healthy control (HC) subjects using different classification techniques. These techniques include linear support vector machine (LSVM), and regularized extreme learning machine (RELM). We used pairwise Pearson’s correlation-based functional connectivity to construct the brain network. We compare the classification performance of brain network using Alzheimer’s disease neuroimaging initiative (ADNI) datasets. Node2vec graph embedding approach is employed to convert graph features to feature vectors. Experimental results show that the SVM with LASSO feature selection method generates better classification accuracy compared to other classification technique.
Highlights
Alzheimer’s disease (AD), which causes majority of dementia is a progressive neurodegenerative disease (American Psychiatric Association, 1994; Liu F. et al, 2014; Schmitter et al, 2015; Alzheimer’s association, 2016)
Elements on the diagonal elements of the matrix specify the accurate estimations by the classifier. These elements are further divided as true positive (TP) and true negative (TN), which signifies appropriately recognized controls
All the erroneously classified matters can be symbolized by false positive (FP) and false negative (FN)
Summary
Alzheimer’s disease (AD), which causes majority of dementia is a progressive neurodegenerative disease (American Psychiatric Association, 1994; Liu F. et al, 2014; Schmitter et al, 2015; Alzheimer’s association, 2016). There is no cure and treatment to slow or stop its progression. Accurate diagnosis of disease at its early stage makes great significance in such scenario. With the availability of recent neuroimaging technology, promising result is obtained in the early and accurate detection of AD (Hanyu et al, 2010; Górriz et al, 2011; Gray et al, 2012). The study of progression of disease and early detection is carried out by using different imaging models, such as electroencephalography (EEG) (Pfefferbaum et al, 2000), functional magnetic resonance imaging (fMRI) (Masliah et al, 1993), single-photon emission computed tomography (SPECT) (Chen et al, 2013) and positron emission tomography (PET) (Ly et al, 2014)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
